Paper Titles

Flow Stoppage in the Middle Area of Flow Length Occurs at Thin Die Gap
p.1

Three-Dimensional Geometrically Exact Dynamic Modeling of Electrohydrodynamic Direct-Writing under a Non-Uniform Electric Field
p.9

Electrohydrodynamic Printing Droplet Volume Control Using Supervised Learning
p.17

Experimental Validation of EMIS-Based Frequency Tracking for Milling Vibration Monitoring Compared with FFT Analysis
p.23

FRT-Net: A Lightweight Frequency-Spatial Framework for Low-Light Enhancement via Retinex Decomposition and FFT Filtering
p.33

Performance Analysis of a 20 Gbps Bidirectional TWDM PON for Different Modulation Formats
p.49

Experimental Investigation of Corona Discharge in Wire-Cylinder Electrostatic Precipitators
p.61

Effects of Staircase Core Configuration on the Seismic Behaviour of Reinforced Concrete Frame Structures
p.73

HomeAdvanced Engineering ForumAdvanced Engineering Forum Vol. 59FRT-Net: A Lightweight Frequency-Spatial Framework...

FRT-Net: A Lightweight Frequency-Spatial Framework for Low-Light Enhancement via Retinex Decomposition and FFT Filtering

Article Preview

Abstract:

In response to the challenges of low brightness, low contrast, and severe noise in low-light images, this paper proposes a lightweight, multi-scale, frequency- and spatial-domain collaborative low-light image enhancement network—FRT-Net. This method integrates classical Retinex theory with modern deep learning techniques. The Retinex decomposition module explicitly separates reflectance and illumination, providing the network with physical interpretability. A multi-scale feature extraction module is designed to capture global brightness trends and local texture details in parallel. Additionally, a frequency-domain FFT filtering branch is introduced to address spectral deficiencies and suppress noise. The CBAM attention mechanism is embedded to adaptively recalibrate channel and spatial weights, enhancing key feature representation. Finally, a comprehensive loss function is employed to collaboratively optimize brightness enhancement, detail recovery, color fidelity, and noise suppression. Experimental results on three mainstream benchmark datasets—LOLv1, LOLv2_real, and LOLv2_syn—demonstrate that FRT-Net ranks among the top two methods in terms of PSNR, SSIM, and LPIPS metrics, achieving an average PSNR of 22.98 dB, SSIM of 0.866, and LPIPS of only 0.075. The model contains only 0.55 million parameters(M) and requires 32.81 GFLOPs, meeting the real-time application demands of mobile devices. Ablation studies verify the effectiveness of each module. With its excellent performance and lightweight design, FRT-Net provides an efficient and robust visual perception foundation for practical applications such as nighttime autonomous driving and security surveillance.

You might also be interested in these eBooks

Advanced Engineering Forum Vol. 59

Info:

Periodical:

Advanced Engineering Forum (Volume 59)

Pages:

33-48

DOI:

https://doi.org/10.4028/p-MH2HkP

Citation:

Cite this paper

Online since:

June 2026

Authors:

Dong Guo*, Yi Han

Keywords:

Attention Mechanism, Deep Learning, Low-Light Image Enhancement, Multi-Scale Features, Retinex Theory

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

© 2026 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

* - Corresponding Author

[1] Li, G., et al., Low-light multimodal object detection: A survey. Computer Science Review, 58 (2025) 100804-100837.

[2] Liao, P., et al., Enhanced Multi-Object Tracking: Inferring Motion States of Tracked Objects. ACM Transactions on Multimedia Computing, Communications and Applications, 21 (2025) 1-25.

DOI: 10.1145/3699960

[3] Qiao, Y., et al., SFANet: Semantic feature aware for domain generalized semantic segmentation. Engineering Applications of Artificial Intelligence, 160 (2025) 111827-111840.

DOI: 10.1016/j.engappai.2025.111827

[4] Stark, J.A., Adaptive image contrast enhancement using generalizations of histogram equalization. IEEE Transactions on Image Processing, 9 (2000) 889 - 896.

DOI: 10.1109/83.841534

[5] Jobson, D.J., Z. Rahman, and G.A. Woodell, A multiscale retinex for bridging the gap between color images and the human observation of scenes. IEEE Transactions on Image Processing 6(1997) 965 - 976.

DOI: 10.1109/83.597272

[6] Sun, Y., et al., Unsupervised detail and color restorer for Retinex-based low-light image enhancement. Engineering Applications of Artificial Intelligence, 153 (2025) 110867-110877.

DOI: 10.1016/j.engappai.2025.110867

[7] Abbass, M.Y., H. Kasban, and Z.F. Elsharkawy, Low-light image enhancement via improved lightweight YUV attention network. Computers & Graphics, 127 (2025) 104170-104182.

DOI: 10.1016/j.cag.2025.104170

[8] Xu, S., et al., An unsupervised fine-tuning strategy for low-light image enhancement. Journal of Visual Communication and Image Representation, 110 (2025) 104480-104495.

DOI: 10.1016/j.jvcir.2025.104480

[9] Abdullah-Al-Wadud, M., et al. A dynamic histogram equalization for image contrast enhancement. in 2007 Digest of Technical Papers International Conference on Consumer Electronics. 2007.

DOI: 10.1109/icce.2007.341567

[10] Fu, X., et al., A probabilistic method for image enhancement with simultaneous illumination and reflectance estimation. IEEE Transactions on Image Processing, 24 (2015) 4965 - 4977.

DOI: 10.1109/tip.2015.2474701

[11] Wang, T., et al. Ultra-high-definition low-light image enhancement: a benchmark and transformer-based method. in Proceedings of the AAAI Conference on Artificial Intelligence. 2023.

DOI: 10.1609/aaai.v37i3.25364

[12] Fu, H., et al. You do not need additional priors or regularizers in Retinex-based low-light image enhancement. in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2023.

DOI: 10.1109/cvpr52729.2023.01738

[13] Jiang, Y., et al., EnlightenGAN: deep light enhancement without paired supervision. IEEE Transactions on Image Processing 30 (2021) 2340 - 2349.

DOI: 10.1109/tip.2021.3051462

[14] Goodfellow, I.J., et al. Generative adversarial nets. in NIPS'14: Proceedings of the 28th International Conference on Neural Information Processing Systems. 2014.

[15] Liu, X., et al., LAE-net: A locally-adaptive embedding network for low-light image enhancement. Pattern Recognition, 133 (2023) 109039-109050.

DOI: 10.1016/j.patcog.2022.109039

[16] Wang, Y., et al. Low light image enhancement with normalizing flow. in Proceedings of the AAAI Conference on Artificial Intelligence. 2022.

[17] Zhang, Y., J. Zhang, and X. Guo. Kindling the Darkness: A Practical Low-light Image Enhancer. in 27th ACMInternational Conference on Multimedia. 2019.

DOI: 10.1145/3343031.3350926

[18] Zhu, M., et al. EEMEFN:Low-Light Image Enhancement via Edge-Enhanced Multi-Exposure Fusion Network. in The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20). 2020.

DOI: 10.1609/aaai.v34i07.7013

[19] Zhang, Y., et al., Beyond Brightening Low-light Images. International Journal of Computer Vision, (2021) 1013–1037.

[20] Dang, J., Y. Zhong, and X. Qin, PPformer: Using Pixel-Wise and Patch-Wise Cross-Attention for Low-Light Image Enhancement. Computer Vision and Image Understanding, 241 (2024) 103930-103942.

DOI: 10.1016/j.cviu.2024.103930

[21] Liu, K., et al., Continuous detail enhancement framework for low-light image enhancement. Displays, 88 (2025) 103040-103054.

DOI: 10.1016/j.displa.2025.103040

[22] Zamir, S.W., et al. Learning enriched features for real image restoration and enhancement. in European Conference on Computer Vision (ECCV). 2020.

[23] Lu, K. and L. Zhang, TBEFN: A Two-Branch Exposure-Fusion Network for Low-Light Image Enhancement. IEEE Transactions on Multimedia, 23 (2020) 4093 - 4105.

DOI: 10.1109/tmm.2020.3037526

[24] Lv, F., et al. MBLLEN: Low-light image/video enhancement using CNNs. in British Machine Vision Conference. 2018.

[25] Lv, F., Y. Li, and F. Lu, Attention guided low-light image enhancement with a large scale low-light simulation dataset. International Journal of Computer Vision, 129 (2021) 2175–2193.

DOI: 10.1007/s11263-021-01466-8

[26] Du, S., et al., A decoupled framework for low-light image enhancement. Expert Systems With Applications, 297 (2025) 129436-129450.

DOI: 10.1016/j.eswa.2025.129436

[27] Loshchilov, I. and F. Hutter. SGDR: Stochastic Gradient Descent with Warm Restarts. in ICLR. 2017.

[28] Wei, C., et al. Deep retinex decomposition for low-light enhancement. in BMVC. 2018.

[29] Yang, W., et al., Sparsegradient regularized deep Retinex network for robust low-light image enhancement. IEEE Transactions on Image Processing, 30 (2021) 2072 - 2086.

DOI: 10.1109/tip.2021.3050850

[30] Wang, R., et al. Underexposed Photo Enhancement Using Deep Illumination Estimation. in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2019.

DOI: 10.1109/cvpr.2019.00701

[31] Moran, S., et al. DeepLPF: deep local parametric filters for image enhancement. in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020.

DOI: 10.1109/cvpr42600.2020.01284

[32] Chen, H., et al. Pre-trained image processing transformer. in IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021.

DOI: 10.1109/cvpr46437.2021.01212

[33] Liu, R., et al. Retinex-inspired unrolling with cooperative prior architecture search for low-light image enhancement. in IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021.

DOI: 10.1109/cvpr46437.2021.01042

[34] Wang, Z., et al. Uformer: A general u-shaped transformer for image restoration. in 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2022.

DOI: 10.1109/cvpr52688.2022.01716

[35] Wei, C., et al. Deep Retinex Decomposition for Low-Light Enhancement. in British Machine Vision Conference. 2018.

[36] Wu, H., et al., CSPN: A Category-specific Processing Network for Low-light Image Enhancement. IEEE Transactions on Circuits and Systems for Video Technology, 34 (2024) 11929 - 11941.

DOI: 10.1109/tcsvt.2024.3426527

[37] Zheng, N., et al. Empowering Low-Light Image Enhancer through Customized Learnable Priors. in IEEE International Conference on Computer Vision. 2023.

DOI: 10.1109/iccv51070.2023.01154

[38] Xu, J., et al., Illumination Guided Attentive Wavelet Network for Low-Light Image Enhancement. IEEE Transactions on Multimedia, 25 (2022) 6258 - 6271.

DOI: 10.1109/tmm.2022.3207330

[39] Zamir, S.W., et al., Learning enriched features for fast image restoration and enhancement. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45 (2022) 1934–1948.

DOI: 10.1109/tpami.2022.3167175

[40] Yang, S., et al. Implicit neural representation for cooperative low-light image enhancement. in Proceedings of the IEEE International Conference on Computer Vision (ICCV). 2023.

DOI: 10.1109/iccv51070.2023.01187

[41] Ma, L., et al. Toward fast, flexible, and robust low-light image enhancement. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022.

DOI: 10.1109/cvpr52688.2022.00555

[42] Guo, C., et al. Zero-reference deep curve estimation for low-light image enhancement. in 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020.

DOI: 10.1109/cvpr42600.2020.00185

[43] Zheng, C., D. Shi, and W. Shi. Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement. in 2021 IEEE/CVF International Conference on Computer Vision (ICCV). 2021.

DOI: 10.1109/iccv48922.2021.00440

[44] Luo, Y., et al., Unsupervised Low-Light Image Enhancement With Self-Paced Learning. IEEE Transactions on Multimedia, 27 (2025) 1808 - 1820.

DOI: 10.1109/tmm.2024.3521752

[45] Li, J., et al., Luminance-aware pyramid network for low-light image enhancement. IEEE Transactions on Multimedia, 23 (2020) 3153 - 3165.

DOI: 10.1109/tmm.2020.3021243

[46] Jiang, H., et al. LightenDiffusion: Unsupervised low-light image enhancement with latent-retinex diffusion models. in European Conference on Computer Vision. 2024.

DOI: 10.1007/978-3-031-73195-2_10

[47] Zamir, S.W., et al. Restormer: efficient transformer for high-resolution image restoration. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2022.

DOI: 10.1109/cvpr52688.2022.00564

[48] Luo, Y., et al., Pseudo-supervised low-light image enhancement with mutual learning. IEEE Transactions on Circuits and Systems for Video Technology, 34 (2024) 85-96.

DOI: 10.1109/tcsvt.2023.3284856

[49] Zhang, Y., J. Zhang, and X. Guo. Kindling the darkness: a practical low-light image enhancer. in Proceedings of the 27th ACM International Conference on Multimedia. 2019.

DOI: 10.1145/3343031.3350926

[50] Guo, H., et al. MambaIR: A simple baseline for image restoration with state-space model. in European Conferenceon Computer Vision. 2024.

[51] Cai, Y., et al. Retinexformer: One-stage retinex-based transformer for low-light image enhancement. in International Conference on Computer Vision. 2023.

DOI: 10.1109/iccv51070.2023.01149

[52] Niu, Y., et al., Adaptive Luminance Enhancement and High-Fidelity Color Correction for Low-Light Image Enhancement. IEEE Transactions on Computational Imaging, 11 (2025) 732 - 747.

DOI: 10.1109/tci.2025.3564112